© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10511
    Prev
    Next
    INDEX
    Explanations

    specific terms related to classification, guidelines, or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "specific", "commercial", or "supplementary"

    np_acts-logits-general · gemini-2.0-flash

    qualifying specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     for
    -0.66
     in
    -0.63
     at
    -0.60
     to
    -0.58
     with
    -0.58
    ,
    -0.57
     as
    -0.57
     by
    -0.56
     on
    -0.56
     from
    -0.55
    POSITIVE LOGITS
     propOrder
    1.05
    RenderAtEndOf
    1.05
     autorytatywna
    1.03
     resourceCulture
    1.01
    GEBURTSDATUM
    0.99
    IndentedString
    0.97
    AddTagHelper
    0.97
     saites
    0.95
     typelib
    0.93
     المعيارى
    0.92
    Activations Density 0.674%

    No Known Activations